© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99025
    Prev
    Next
    INDEX
    Explanations

    inhale or inhalation context

    np_acts-logits-general · gemini-2.5-flash-lite

    references to inhalation or breathing in substances, particularly related to respiratory processes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h4>
    -1.88
    </u>
    -1.86
     does
    -1.79
    */
    -1.76
    ↵↵↵
    -1.71
    </h3>
    -1.68
    or
    -1.67
    ā
    -1.67
    ",
    -1.66
    If
    -1.65
    POSITIVE LOGITS
    罍
    1.75
    妧
    1.66
    罴
    1.63
     起毛
    1.59
     花纹
    1.58
    wants
    1.58
     放題
    1.56
     rangs
    1.55
     choses
    1.52
    reached
    1.50
    Activations Density 0.019%

    No Known Activations